© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 181316
    Prev
    Next
    INDEX
    Explanations

    performance and skill

    np_acts-logits-general · gemini-2.5-flash-lite

    conjunctions and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出荷
    0.47
    騾
    0.41
     Çünkü
    0.41
    鱔
    0.41
    രുത്
    0.40
    ాలలో
    0.40
     Identifier
    0.39
    ಲ
    0.39
    FileSize
    0.38
    品番
    0.38
    POSITIVE LOGITS
    他也
    0.50
    stantial
    0.47
     він
    0.45
     året
    0.44
     семья
    0.44
     refiere
    0.43
    เขา
    0.43
     hän
    0.42
    mprj
    0.42
     vrch
    0.41
    Activations Density 0.000%

    No Known Activations